A group of “unauthorized users” have accessed Anthropic’s Mythos AI model, which the company recently said they couldn’t widely release because it was too dangerous. Maybe don’t use guessable paths for your powerful cyberattack model.
A group of "unauthorized users" have...
Continue Reading on Kottke.org
This article continues with additional insights and analysis. Read the full article for free.
Read Full Article on Kottke.org